Ffsgc-Based Classification of Environmental Factors in IOT Sports Education Data during the Covid-19 Pandemic

Abstract

The COVID-19 pandemic has posed unprecedented challenges to sports education, requiring the implementation of rigorous measures to ensure the safety of athletes and staff. In this context, the integration of Internet of Things (IoT) technologies, deep learning image processing, and sustainable optimization The Fruitfly Statistical Gradient Classifier (FfSGC) is a novel algorithm developed to address the challenges of classification tasks in the context of IoT sports education data during the COVID-19 pandemic. This algorithm combines fuzzy set theory and Least Absolute Shrinkage and Selection Operator (LASSO) to effectively handle the uncertainty and imprecision inherent in the dataset. The FfSGC algorithm incorporates feature selection and extraction techniques, such as Fruitfly optimization and Principal Component Analysis (PCA), to identify the most relevant features for classification. By considering the impact of COVID-19 on player performance, environmental factors, injury risk, and training load, the algorithm enables accurate and robust classification. Simulation experiments were conducted using different datasets related to player performance, environmental factors, injury risk, and training load. The results showed that the FfSGC algorithm consistently achieved high accuracy, precision, recall, F1-score, and mean squared error across the datasets. Compared to existing classification algorithms like SVM and Random Forest, FfSGC demonstrated superior performance in terms of classification metrics. The FfSGC algorithm has significant implications for the sports education domain during the COVID-19 pandemic. It provides valuable insights for decision-making processes related to COVID-19 prevention and control strategies in sports settings.